Parallel video generation and two new models are now live.

Parallel generations: all video generation apps can now create multiple videos at once, running in parallel.
WAN 3.0: native audio, enhanced reasoning, prompt-driven generation or first/last-frame animation, and clips from 2 to 30 seconds at 480p, 720p, or 1080p. Text-to-Video Image-to-Video
MiniMax H3 Max: native audio, incredibly fast generation, prompt expansion, and clips up to 15 seconds at 480P or 768P. Text-to-Video Image-to-Video

Prompt

Describe the scene and motion to generate.

Image

Upload the first frame image to animate.

Duration

The duration of the video in seconds

Resolution

The native resolution of the generated video.

480P

Available in Power Mode

Count

Number of results to generate in parallel.

More options

End image

Upload an optional final frame image.

Seed

Unique output seed number. If not provided, the output will be random.

Prompt expansion mode

Choose how much effort is spent expanding the prompt.

Balanced

This is a SFW (Safe For Work) only model.